New Your team’s decisions, in one playbook every coding agent works from. Never answer your agent twice

system_open_url

Open URL in device browser

SERVERClaude Mobile SOURCEalexgladkov/claude-in-mobile
High RISK CLASS
Category Execute
Parameters 00 required
Recommended Rate-limitedsee the rule below
Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/alexgladkov-claude-in-mobile/system-open-url.md

What system_open_url does on Claude Mobile

AI agents invoke system_open_url to trigger actions in Claude Mobile. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call: builds kicked off, notifications sent, workflows started.

Why system_open_url is rated High

Opening a URL in a device browser is an Execute-category action: it triggers an external operation whose effects depend entirely on the URL argument. An attacker or misconfigured agent could navigate to malicious sites, trigger drive-by downloads, invoke deep links that launch apps or authorize OAuth flows, or exfiltrate data. It does not merely read data — it actively causes the device to perform an action.

From the tool's definition 'Open URL in device browser' — triggers an external operation (opening a URL) on a mobile device via browser automation

Risk signalsAdmin/system-level operation

Questions about system_open_url

What does the system_open_url tool do? +

Open URL in device browser. It is categorised as a Execute tool in the Claude Mobile MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on system_open_url? +

Register the Claude Mobile MCP server in PolicyLayer and add a rule for system_open_url: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Claude Mobile. Nothing to install.

What risk level is system_open_url? +

system_open_url is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit system_open_url? +

Yes. Add a rate_limit block to the system_open_url rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.

How do I block system_open_url completely? +

Set action: deny in the PolicyLayer policy for system_open_url. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.

What MCP server provides system_open_url? +

system_open_url is provided by the Claude Mobile MCP server (alexgladkov/claude-in-mobile). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

More on Claude Mobile, and thousands of servers like it.

// THE MCP REGISTRY

PolicyLayer tracks 44,603 MCP servers and 515,000+ tools.

Every server has a live record: who publishes it, whether it answers without auth, its risk grade, every tool classified, the recommended policy. This page is one line of Claude Mobile's. Pull the full record:

Teams ship this data inside their own products. See what a licence covers →

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.